Global Group Fairness in Federated Learning via Function Tracking

2025/03/19 by Yves Rychener, Daniel Kühn, Rychener, Yves +3
Computer Science · Social Sciences · #Ethics and Social Impacts of AI #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Methodology (stat.ME) #Mobile Crowdsensing and Crowdsourcing #Optimization and Control (math.OC) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2503.15163

openalex publication_date 2025/03/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We investigate group fairness regularizers in federated learning, aiming to train a globally fair model in a distributed setting. Ensuring global fairness in distributed training presents unique challenges, as fairness regularizers typically involve probability metrics between distributions across all clients and are not naturally separable by client. To address this, we introduce a function-tracking scheme for the global fairness regularizer based on a Maximum Mean Discrepancy (MMD), which incurs a small communication overhead. This scheme seamlessly integrates into most federated learning algorithms while preserving rigorous convergence guarantees, as demonstrated in the context of FedAvg. Additionally, when enforcing differential privacy, the kernel-based MMD regularization enables straightforward analysis through a change of kernel, leveraging an intuitive interpretation of kernel convolution. Numerical experiments confirm our theoretical insights.

Cited by

• FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluation

Related

• Mitigating Group Bias in Federated Learning: Beyond Local Fairness
• FAIRVAR: Fair Federated Learning via Variance Regularization
• FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning
• Unified Group Fairness on Federated Learning
• GLOCALFAIR: Jointly Improving Global and Local Group Fairness in Federated Learning